modelKrigingInit: Kriging: Initial guess and bounds

In CEGO: Combinatorial Efficient Global Optimization

Kriging: Initial guess and bounds

Description

Initialize parameter tuning for the Kriging model, setting the initial guess as well as bound constraints.

Usage

modelKrigingInit(
  startTheta = NULL,
  lowerTheta = NULL,
  upperTheta = NULL,
  useLambda,
  lambdaLower,
  lambdaUpper,
  combineDistances,
  nd,
  distanceParameters = F,
  distanceParametersLower = NA,
  distanceParametersUpper = NA
)

Arguments

startTheta	user provided start guess (optional).
lowerTheta	lower boundary for theta values (log scale), the kernel parameters.
upperTheta	upper boundary for theta values (log scale), the kernel parameters.
useLambda	boolean, whether nugget effect (lambda) is used.
lambdaLower	lower boundary for lambda (log scale).
lambdaUpper	upper boundary for lambda (log scale).
combineDistances	boolean, whether multiple distances are combined.
nd	number of distance function.
distanceParameters	whether the distance function parameters should be optimized
distanceParametersLower	lower boundary for parameters of the distance function, default is NA which means there are no distance function parameters. If several distance functions are supplied, this should be a list of lower boundary vectors for each function.
distanceParametersUpper	upper boundary for parameters of the distance function, default is NA which means there are no distance function parameters. If several distance functions are supplied, this should be a list of upper boundary vectors for each function.

Value

a list with elements x0 (start guess), lower (lower bound), upper (upper bound).

See Also

modelKriging

CEGO documentation built on May 29, 2024, 3:35 a.m.